CN109631848A - Electric line foreign matter intruding detection system and detection method - Google Patents
Electric line foreign matter intruding detection system and detection method Download PDFInfo
- Publication number
- CN109631848A CN109631848A CN201811533798.0A CN201811533798A CN109631848A CN 109631848 A CN109631848 A CN 109631848A CN 201811533798 A CN201811533798 A CN 201811533798A CN 109631848 A CN109631848 A CN 109631848A
- Authority
- CN
- China
- Prior art keywords
- electricity
- transmission line
- foreign body
- foreign matter
- image data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of electric line foreign matter intruding detection system and detection method based on Parallel neural networks can timely and effectively find that electric line foreign matter is invaded, not only substantially increase the accuracy rate of foreign body intrusion detection, it is ensured that detection efficiency.Detection method includes the following steps for this: transmission line of electricity being divided into several segments, obtains the image data of every section of transmission line of electricity;Gray proces are carried out to every section of transmission line of electricity of image data respectively;Foreign body intrusion detection is carried out to obtained each gray level image respectively using trained Parallel neural networks;If detecting foreign body intrusion, it will test result and corresponding image data be sent to background storage server and stored.
Description
Technical field
This disclosure relates to transmission line faultlocating field, and in particular to a kind of embedded power transmission line based on Parallel neural networks
Road foreign body intrusion detection system and detection method.
Background technique
With the rapid economic development in our country, guaranteeing that power supply and demand is securely and reliably most important.Since transmission line of electricity is long-term
It is exposed in field environment, foreign matter often occurs and hangs on high-voltage line and foreign body intrusion damage line facility, causes to fall line, combustion
Burning, route damage etc., not only cause serious economic loss, but also can cause to the vehicle under transmission line of electricity, pedestrian can not
The harm retrieved.Therefore, discovery foreign body intrusion and early warning accurately and timely has safely very China's grid power transmission route
Important meaning.
The detection for electric line foreign matter invasion mainly has manual inspection and unmanned plane inspection at present.Transmission line of electricity is usual
By the geographical environment of the complexity such as mountains and rivers river, highway bridge, for artificial line walking method there are biggish security risk, waste is a large amount of
Manpower and material resources, and the problems such as there are routing inspection efficiency is low and inspection effect is poor.Then, occur by aircraft as delivery work
Tool loads the unmanned plane inspection method that visual light imaging equipment carries out inspection to 110~1000KV high voltage transmission line corridor.Although it
Do not influenced by geographical environment, but the great amount of images data passed back of unmanned vehicle still need artificially to judge be on route
It is no that there are foreign matters.Both the above method is required to artificial detection, can not find foreign body intrusion in time.
In addition, popularizing with monitoring device, the electric line foreign matter intrusion detection based on image procossing is also that one kind can
Capable method.Foreign body intrusion detection method is made an uproar generally by the elimination of gaussian filtering, median filtering or bilateral filtering at present
Sound carries out the segmentation of background and prospect using maximum between-cluster variance (Otsu) to image, finally extracts transmission of electricity using Hough transform
Route, then foreign matter is identified.However, transmission line of electricity is exposed to field throughout the year, influenced by weather, illumination and geographical environment
Larger, it is difficult to extract accurately and effectively background informations, and transmission line of electricity substantial amounts, the video image for obtaining camera shooting are believed
Breath needs the network communication expense of both expensive, is difficult timely and effectively to find foreign body intrusion.
In conclusion foreign matter enters at present for can not timely and effectively find that electric line foreign matter is invaded in complex scene
The low problem of Detection accuracy is invaded, still shortage effective solution scheme.
Summary of the invention
In order to solve the problems, such as in complex scene that electric line foreign matter Detection accuracy is low, not in time, present disclose provides
A kind of electric line foreign matter intruding detection system and detection method based on Parallel neural networks, can timely and effectively find defeated
Electric line foreign body intrusion not only substantially increases the accuracy rate of foreign body intrusion detection, it is ensured that detection efficiency.
Technical solution used by the disclosure is:
A kind of electric line foreign matter intrusion detection method, method includes the following steps:
Transmission line of electricity is divided into several segments, obtains the image data of every section of transmission line of electricity;
Gray proces are carried out to every section of transmission line of electricity of image data respectively;
Foreign body intrusion detection is carried out to obtained each gray level image respectively using trained Parallel neural networks;
If detecting foreign body intrusion, it will test result and corresponding image data be sent to background storage server progress
Storage.
Further, the acquisition methods of the image data of every section of the transmission line of electricity are as follows:
Every section in transmission line of electricity is respectively set camera and processor, is obtained by processor when preceding camera acquisition
Video flowing, and video flowing is decoded, generate image data.
Further, the Parallel neural networks include feature extraction layer and several network structure layers in parallel.
Further, the method that foreign body intrusion detection is carried out to gray level image using trained Parallel neural networks
Are as follows:
Parallel neural networks are trained using foreign body intrusion data set;
Gray level image is input in trained Parallel neural networks;
By feature extraction layer, characteristic pattern is extracted;
Characteristic pattern is divided into several net regions;
Each net region is input to heterogeneous networks structure sheaf in parallel to handle, obtains classification results;
The classification results of each network structure layer are merged, judgment matrix is obtained;
Judge transmission line of electricity with the presence or absence of foreign body intrusion using judgment matrix.
Further, each network structure layer include two convolutional layers, a pond layer, a full articulamentum and
SVM classifier.
Further, element number is identical as net region number in the judgment matrix, each element in judgment matrix
Current region is represented with the presence or absence of foreign body intrusion, and if it exists, then element is 1, and if it does not exist, then element is 0.
It is further, described to judge that transmission line of electricity whether there is the method for foreign body intrusion using judgment matrix are as follows:
If all elements are not 0 in judgment matrix, this section of transmission line of electricity there are foreign body intrusion, by the judgment matrix and
The image data of this section of transmission line of electricity is sent to background storage server;
If all elements are 0 in judgment matrix, foreign body intrusion is not present in this section of transmission line of electricity, does not send data.
A kind of electric line foreign matter intruding detection system, the system are invaded for realizing electric line foreign matter as described above
Detection method, the system include each and every one several cameras, the processor connecting with each camera and storage server;
The camera for acquiring the video flowing of every section of transmission line of electricity, and is sent to processor.
The processor for obtaining the video flowing for working as preceding camera acquisition, and is decoded video flowing, generates figure
Picture carries out gray proces to image, obtains gray level image;Gray level image is input in trained Parallel neural networks and is carried out
Foreign body intrusion detection, if detecting foreign body intrusion, will test result and corresponding image data is sent to storage server;
The storage server, for storing the testing result of invasion image data and the intruding image data.
Through the above technical solutions, the beneficial effect of the disclosure is:
(1) disclosure can realize image detection processing in front end by access embeded processor, only need to be by abnormal letter
Breath returns to server, and network transmission resource is greatly saved;
(2) disclosure carries out detection processing to live image by Parallel neural networks, can accurately and effectively find different
Object invades situation, and is adapted to different types of foreign body intrusion, and also has detection effect well to new foreign body intrusion
Fruit.
Detailed description of the invention
The Figure of description for constituting a part of this disclosure is used to provide further understanding of the disclosure, and the disclosure is shown
Meaning property embodiment and its explanation do not constitute the improper restriction to the disclosure for explaining the application.
Fig. 1 is the structure chart of electric line foreign matter intruding detection system;
Fig. 2 is the flow chart of electric line foreign matter intrusion detection method;
Fig. 3 is the flow chart for carrying out foreign body intrusion detection to gray level image using trained Parallel neural networks.
Specific embodiment
The disclosure is described further with embodiment with reference to the accompanying drawing.
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the disclosure.Unless another
It indicates, all technical and scientific terms that the disclosure uses have logical with disclosure person of an ordinary skill in the technical field
The identical meanings understood.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
One or more embodiments provide a kind of electric line foreign matter intruding detection system, which includes several camera shootings
Head, the processor being connect with each camera and storage server, as shown in Figure 1.
The camera for acquiring the video flowing of every section of transmission line of electricity, and is sent to processor.
The processor uses TX2 development board, carries out for obtaining the video flowing for working as preceding camera acquisition, and to video flowing
Decoding generates image, carries out gray proces to image, obtains gray level image;Gray level image is input to trained mind in parallel
Through carrying out foreign body intrusion detection in network, if will detect intrusion target, will test result and intruding image be sent to from the background
Storage server;
The storage server, for storing the testing result of intruding image He the intruding image.
In the present embodiment, transmission line of electricity is divided into several segments, be respectively provided on every section of transmission line of electricity camera and
Processor, the video flowing of every section of transmission line of electricity is acquired by camera, and is sent to processor;Processor is to every section of transmission line of electricity
Video flowing be decoded to obtain the image of every section of transmission line of electricity, detection processing is carried out to every section of transmission line of electricity of image, in time
It was found that on transmission line of electricity every section whether have foreign body intrusion.
The electric line foreign matter intruding detection system that the present embodiment proposes, using multiple cameras and multiple embedded processings
Trained neural network model is deployed in embeded processor by device, can be taken the photograph by each processor to each in front end
The image acquired as head carries out detection processing, foreign body intrusion hidden danger is found in time, by nerual network technique and image processing techniques
It combines, improves the speed and precision of detection.
One or more embodiments provide a kind of electric line foreign matter intrusion detection method, and this method is based on as described above
What electric line foreign matter intruding detection system was realized, as shown in Fig. 2, method includes the following steps:
Transmission line of electricity is divided into several segments, obtains the image data of every section of transmission line of electricity by S101.
In at least one embodiment, camera and processor is respectively set at every section of transmission line of electricity, passes through processor
The video flowing when preceding camera acquisition is obtained, and video flowing is decoded, generates the image of every section of transmission line of electricity.
S102 carries out gray proces to every section of transmission line of electricity of image respectively, obtains the gray level image of every section of transmission line of electricity.
In order to avoid the influence that illumination shade detects foreign body intrusion, RGB image is converted to gray level image by processor.
S103 is utilized respectively trained Parallel neural networks to the grayscale image of every section obtained of transmission line of electricity of step S102
As carrying out foreign body intrusion detection.
In the present embodiment, the Parallel neural networks include feature extraction layer and several network structure layers in parallel.
In the step S103, the side of foreign body intrusion detection is carried out to gray level image using trained Parallel neural networks
Method specifically:
S103-1 is trained Parallel neural networks using foreign body intrusion data set.
In the step S103-1, the method being trained using foreign body intrusion data set to Parallel neural networks is specific
Are as follows:
Training dataset is divided by 7:3 for training set and test set, Parallel neural networks are input to, using under stochastic gradient
The training method of drop is constantly adjusted initial value, training rate and the number of iterations according to intermediate result, obtain it is optimal and
Join neural network.
S103-2 carries out foreign body intrusion detection to gray level image using trained Parallel neural networks.
The specific implementation of the step S103-2 is as follows:
(1) gray level image is input in trained Parallel neural networks;
(2) pass through feature extraction layer, extract sharing feature figure;By 2 convolutional layers and a pond layer, it is special to generate image
Sign figure;
(2) characteristics of image figure is divided into several net regions;
(3) each net region is input to heterogeneous networks structure sheaf in parallel to handle, area is extracted by convolution
Convolution feature is input to SVM classifier, obtains classification results by characteristic of field;Wherein, each network structure layer in parallel includes
2 convolutional layers, 1 pond layer, 1 full articulamentum and SVM classifier.Classification results include there are foreign body intrusion and there is no different
Object invasion;
(4) classification results of each network structure layer in parallel are merged, obtains judgment matrix, it is every in judgment matrix
A element represents current region with the presence or absence of foreign body intrusion, and if it exists, then element is 1, and if it does not exist, then element is 0;
(5) transmission line of electricity section is judged with the presence or absence of foreign body intrusion, if all elements in judgment matrix using judgment matrix
It is not 0, then there are foreign body intrusions for this section of transmission line of electricity, send the image data of the judgment matrix He this section of transmission line of electricity to
Background storage server;If all elements are 0 in judgment matrix, foreign body intrusion is not present in this section of transmission line of electricity, is not sent
Data.
As shown in figure 3, the size of the gray level image of input Parallel neural networks is 512 × 512, feature extraction is first passed around
Layer extracts sharing feature figure, by 2 convolutional layers and 1 pond layer, generates 128 × 128 characteristics of image figure;It then will figure
As characteristic pattern is divided into 8 × 8=64 net region, it is separately input to heterogeneous networks structure sheaf in parallel, by each network knot
The classification results of structure layer generate 8 × 8 judgment matrix after merging, each element, which represents current region, in judgment matrix whether there is
Foreign body intrusion exists for 1, and there is no be 0.
The present embodiment proposes a kind of Parallel neural networks, and nerual network technique and image processing techniques are combined, and improves
The speed and precision of detection;Trained neural network model is deployed to embeded processor, it can be in front end to camera shooting
The image of head acquisition carries out detection processing, finds foreign body intrusion hidden danger in time.
S104 will test result and image be sent to background storage server and stored if detecting intrusion target.
If it find that transmission line of electricity has foreign body intrusion, background storage server is sent by image and testing result information,
Intruding image is only sent, network transmission bandwidth can be greatlyd save.
The electric line foreign matter intrusion detection method that the present embodiment proposes, image procossing is mutually tied with Parallel neural networks
It closes, effectively increases the robustness and accuracy that foreign body intrusion detects in transmission line of electricity scene;Model is deployed to embedded system
System, realizes the front-end processing of image, network bandwidth is greatly saved, improve detection efficiency.
Although above-mentioned be described in conjunction with specific embodiment of the attached drawing to the disclosure, model not is protected to the disclosure
The limitation enclosed, those skilled in the art should understand that, on the basis of the technical solution of the disclosure, those skilled in the art are not
Need to make the creative labor the various modifications or changes that can be made still within the protection scope of the disclosure.
Claims (8)
1. a kind of electric line foreign matter intrusion detection method, characterized in that method includes the following steps:
Transmission line of electricity is divided into several segments, obtains the image data of every section of transmission line of electricity;
Gray proces are carried out to every section of transmission line of electricity of image data respectively;
Foreign body intrusion detection is carried out to obtained each gray level image respectively using trained Parallel neural networks;
If detecting foreign body intrusion, it will test result and corresponding image data be sent to background storage server and deposited
Storage.
2. electric line foreign matter intrusion detection method according to claim 1, characterized in that every section of the transmission line of electricity
The acquisition methods of image data are as follows:
Every section in transmission line of electricity is respectively set camera and processor, obtains the video when preceding camera acquisition by processor
Stream, and video flowing is decoded, generate image data.
3. electric line foreign matter intrusion detection method according to claim 1, characterized in that the Parallel neural networks packet
Include feature extraction layer and several network structure layers in parallel.
4. electric line foreign matter intrusion detection method according to claim 3, characterized in that the utilization is trained simultaneously
Join the method that neural network carries out foreign body intrusion detection to gray level image are as follows:
Parallel neural networks are trained using foreign body intrusion data set;
Gray level image is input in trained Parallel neural networks;
By feature extraction layer, characteristic pattern is extracted;
Characteristic pattern is divided into several net regions;
Each net region is input to heterogeneous networks structure sheaf in parallel to handle, obtains classification results;
The classification results of each network structure layer are merged, judgment matrix is obtained;
Judge transmission line of electricity with the presence or absence of foreign body intrusion using judgment matrix.
5. electric line foreign matter intrusion detection method according to claim 4, characterized in that each network structure layer
It include two convolutional layers, a pond layer, a full articulamentum and SVM classifier.
6. electric line foreign matter intrusion detection method according to claim 4, characterized in that element in the judgment matrix
Number is identical as net region number, and each element represents current region with the presence or absence of foreign body intrusion in judgment matrix, and if it exists,
Then element is 1, and if it does not exist, then element is 0.
7. electric line foreign matter intrusion detection method according to claim 4, characterized in that described to be sentenced using judgment matrix
The method that disconnected transmission line of electricity whether there is foreign body intrusion are as follows:
If all elements are not 0 in judgment matrix, transmission line of electricity is there are foreign body intrusion, by judgment matrix and transmission line of electricity
Image data is sent to background storage server;
If all elements are 0 in judgment matrix, foreign body intrusion is not present in transmission line of electricity, does not send data.
8. a kind of electric line foreign matter intruding detection system, the system is for realizing of any of claims 1-7 defeated
Electric line foreign body intrusion detection method, characterized in that including each and every one several cameras, the processor being connect with each camera and
Storage server;
The camera for acquiring the video flowing of every section of transmission line of electricity, and is sent to processor;
The processor for obtaining the video flowing for working as preceding camera acquisition, and is decoded video flowing, generates image, right
Image carries out gray proces, obtains gray level image;Gray level image is input in trained Parallel neural networks and carries out foreign matter
Intrusion detection will test result and corresponding image data be sent to storage server if detecting foreign body intrusion;
The storage server, for storing the testing result of invasion image data and the intruding image data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811533798.0A CN109631848B (en) | 2018-12-14 | 2018-12-14 | Transmission line foreign matter intrusion detection system and detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811533798.0A CN109631848B (en) | 2018-12-14 | 2018-12-14 | Transmission line foreign matter intrusion detection system and detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109631848A true CN109631848A (en) | 2019-04-16 |
CN109631848B CN109631848B (en) | 2021-04-16 |
Family
ID=66073892
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811533798.0A Active CN109631848B (en) | 2018-12-14 | 2018-12-14 | Transmission line foreign matter intrusion detection system and detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109631848B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110730327A (en) * | 2019-09-03 | 2020-01-24 | 华为技术有限公司 | Method for monitoring power transmission line and acquisition front end |
CN110728202A (en) * | 2019-09-23 | 2020-01-24 | 国网宁夏电力有限公司电力科学研究院 | Transmission conductor foreign matter detection method, terminal and system |
CN110807353A (en) * | 2019-09-03 | 2020-02-18 | 国网辽宁省电力有限公司电力科学研究院 | Transformer substation foreign matter identification method, device and system based on deep learning |
CN111325708A (en) * | 2019-11-22 | 2020-06-23 | 济南信通达电气科技有限公司 | Power transmission line detection method and server |
CN111814686A (en) * | 2020-07-09 | 2020-10-23 | 国网山西省电力公司吕梁供电公司 | Vision-based power transmission line identification and foreign matter invasion online detection method |
CN113011252A (en) * | 2021-02-04 | 2021-06-22 | 成都希格玛光电科技有限公司 | Track foreign matter intrusion detection system and method |
CN113160150A (en) * | 2021-04-01 | 2021-07-23 | 西安科技大学 | AI (Artificial intelligence) detection method and device for invasion of foreign matters in wire network based on multi-type sample fusion and multi-complex network |
CN113673514A (en) * | 2021-08-11 | 2021-11-19 | 国网山东省电力公司微山县供电公司 | Method and system for detecting invasion of foreign matters into power transmission line |
CN114627388A (en) * | 2022-03-23 | 2022-06-14 | 南方电网数字电网研究院有限公司 | Power transmission line foreign matter detection equipment and foreign matter detection method thereof |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3647584B2 (en) * | 1996-12-26 | 2005-05-11 | 富士通株式会社 | Learning type self-localization device |
CN103530620A (en) * | 2013-10-30 | 2014-01-22 | 华北电力大学 | Method for identifying bird nest on electric transmission line tower |
CN104463324A (en) * | 2014-11-21 | 2015-03-25 | 长沙马沙电子科技有限公司 | Convolution neural network parallel processing method based on large-scale high-performance cluster |
US20150276980A1 (en) * | 2014-03-31 | 2015-10-01 | Stc.Unm | Apparatus and method for solar energy resource micro-forecasts for solar generation sources and utilities |
US20150339571A1 (en) * | 2012-12-24 | 2015-11-26 | Google Inc. | System and method for parallelizing convolutional neural networks |
CN105467975A (en) * | 2015-12-29 | 2016-04-06 | 山东鲁能软件技术有限公司 | Equipment fault diagnosis method |
CN105574284A (en) * | 2015-12-29 | 2016-05-11 | 山东鲁能软件技术有限公司 | Power equipment fault diagnosis method based on tendency characteristic point |
CN106650786A (en) * | 2016-11-14 | 2017-05-10 | 沈阳工业大学 | Image recognition method based on multi-column convolutional neural network fuzzy evaluation |
CN106778472A (en) * | 2016-11-17 | 2017-05-31 | 成都通甲优博科技有限责任公司 | The common invader object detection and recognition method in transmission of electricity corridor based on deep learning |
CN107680097A (en) * | 2017-10-31 | 2018-02-09 | 湖北中海盛达电力器材有限公司 | A kind of method of electric power line pole tower identification Bird's Nest |
CN107944412A (en) * | 2017-12-04 | 2018-04-20 | 国网山东省电力公司电力科学研究院 | Transmission line of electricity automatic recognition system and method based on multilayer convolutional neural networks |
US20180181822A1 (en) * | 2016-12-27 | 2018-06-28 | Automotive Research & Testing Center | Hierarchical system for detecting object with parallel architecture and hierarchical method thereof |
CN108573228A (en) * | 2018-04-09 | 2018-09-25 | 杭州华雁云态信息技术有限公司 | A kind of electric line foreign matter intrusion detection method and device |
CN108734143A (en) * | 2018-05-28 | 2018-11-02 | 江苏迪伦智能科技有限公司 | A kind of transmission line of electricity online test method based on binocular vision of crusing robot |
-
2018
- 2018-12-14 CN CN201811533798.0A patent/CN109631848B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3647584B2 (en) * | 1996-12-26 | 2005-05-11 | 富士通株式会社 | Learning type self-localization device |
US20150339571A1 (en) * | 2012-12-24 | 2015-11-26 | Google Inc. | System and method for parallelizing convolutional neural networks |
CN103530620A (en) * | 2013-10-30 | 2014-01-22 | 华北电力大学 | Method for identifying bird nest on electric transmission line tower |
US20150276980A1 (en) * | 2014-03-31 | 2015-10-01 | Stc.Unm | Apparatus and method for solar energy resource micro-forecasts for solar generation sources and utilities |
CN104463324A (en) * | 2014-11-21 | 2015-03-25 | 长沙马沙电子科技有限公司 | Convolution neural network parallel processing method based on large-scale high-performance cluster |
CN105574284A (en) * | 2015-12-29 | 2016-05-11 | 山东鲁能软件技术有限公司 | Power equipment fault diagnosis method based on tendency characteristic point |
CN105467975A (en) * | 2015-12-29 | 2016-04-06 | 山东鲁能软件技术有限公司 | Equipment fault diagnosis method |
CN106650786A (en) * | 2016-11-14 | 2017-05-10 | 沈阳工业大学 | Image recognition method based on multi-column convolutional neural network fuzzy evaluation |
CN106778472A (en) * | 2016-11-17 | 2017-05-31 | 成都通甲优博科技有限责任公司 | The common invader object detection and recognition method in transmission of electricity corridor based on deep learning |
US20180181822A1 (en) * | 2016-12-27 | 2018-06-28 | Automotive Research & Testing Center | Hierarchical system for detecting object with parallel architecture and hierarchical method thereof |
CN107680097A (en) * | 2017-10-31 | 2018-02-09 | 湖北中海盛达电力器材有限公司 | A kind of method of electric power line pole tower identification Bird's Nest |
CN107944412A (en) * | 2017-12-04 | 2018-04-20 | 国网山东省电力公司电力科学研究院 | Transmission line of electricity automatic recognition system and method based on multilayer convolutional neural networks |
CN108573228A (en) * | 2018-04-09 | 2018-09-25 | 杭州华雁云态信息技术有限公司 | A kind of electric line foreign matter intrusion detection method and device |
CN108734143A (en) * | 2018-05-28 | 2018-11-02 | 江苏迪伦智能科技有限公司 | A kind of transmission line of electricity online test method based on binocular vision of crusing robot |
Non-Patent Citations (5)
Title |
---|
SHAOQING REN等: "Faster R-CNN Towards Real-Time Object Detection with Region Proposal Networks", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
凡保磊: "卷积神经网络的并行化研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
刘文祺: "基于深度神经网络的铁路异物检测算法", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
张任其 等: "分布式环境下卷积神经网络并行策略研究", 《计算机工程与应用》 * |
王励 等: "基于并行深度卷积神经网络的图像美感分类", 《自动化学报》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110807353B (en) * | 2019-09-03 | 2023-12-19 | 国网辽宁省电力有限公司电力科学研究院 | Substation foreign matter identification method, device and system based on deep learning |
CN110807353A (en) * | 2019-09-03 | 2020-02-18 | 国网辽宁省电力有限公司电力科学研究院 | Transformer substation foreign matter identification method, device and system based on deep learning |
WO2021042682A1 (en) * | 2019-09-03 | 2021-03-11 | 国网辽宁省电力有限公司电力科学研究院 | Method, apparatus and system for recognizing transformer substation foreign mattter, and electronic device and storage medium |
CN110730327A (en) * | 2019-09-03 | 2020-01-24 | 华为技术有限公司 | Method for monitoring power transmission line and acquisition front end |
CN110728202A (en) * | 2019-09-23 | 2020-01-24 | 国网宁夏电力有限公司电力科学研究院 | Transmission conductor foreign matter detection method, terminal and system |
CN111325708A (en) * | 2019-11-22 | 2020-06-23 | 济南信通达电气科技有限公司 | Power transmission line detection method and server |
CN111814686A (en) * | 2020-07-09 | 2020-10-23 | 国网山西省电力公司吕梁供电公司 | Vision-based power transmission line identification and foreign matter invasion online detection method |
CN113011252A (en) * | 2021-02-04 | 2021-06-22 | 成都希格玛光电科技有限公司 | Track foreign matter intrusion detection system and method |
CN113011252B (en) * | 2021-02-04 | 2023-12-05 | 成都希格玛光电科技有限公司 | Rail foreign matter intrusion detection system and method |
CN113160150A (en) * | 2021-04-01 | 2021-07-23 | 西安科技大学 | AI (Artificial intelligence) detection method and device for invasion of foreign matters in wire network based on multi-type sample fusion and multi-complex network |
CN113673514A (en) * | 2021-08-11 | 2021-11-19 | 国网山东省电力公司微山县供电公司 | Method and system for detecting invasion of foreign matters into power transmission line |
CN114627388A (en) * | 2022-03-23 | 2022-06-14 | 南方电网数字电网研究院有限公司 | Power transmission line foreign matter detection equipment and foreign matter detection method thereof |
CN114627388B (en) * | 2022-03-23 | 2024-03-29 | 南方电网数字电网研究院有限公司 | Foreign matter detection equipment and foreign matter detection method for power transmission line |
Also Published As
Publication number | Publication date |
---|---|
CN109631848B (en) | 2021-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109631848A (en) | Electric line foreign matter intruding detection system and detection method | |
CN110070530B (en) | Transmission line icing detection method based on deep neural network | |
CN106971544B (en) | A kind of direct method that vehicle congestion is detected using still image | |
CN103106766A (en) | Forest fire identification method and forest fire identification system | |
CN108806334A (en) | A kind of intelligent ship personal identification method based on image | |
CN109993163B (en) | Non-tag identification system based on artificial intelligence and identification method thereof | |
CN108109385A (en) | A kind of vehicle identification of power transmission line external force damage prevention and hazardous act judgement system and method | |
CN104134067A (en) | Road vehicle monitoring system based on intelligent visual Internet of Things | |
CN103729620A (en) | Multi-view pedestrian detection method based on multi-view Bayesian network | |
CN112287823A (en) | Facial mask identification method based on video monitoring | |
CN110796580A (en) | Intelligent traffic system management method and related products | |
CN110288623A (en) | The data compression method of unmanned plane marine cage culture inspection image | |
Ji et al. | Real-time enhancement of the image clarity for traffic video monitoring systems in haze | |
Yuan et al. | Identification method of typical defects in transmission lines based on YOLOv5 object detection algorithm | |
CN109902730A (en) | Broken strand of power transmission line detection method based on deep learning | |
CN109697410A (en) | A kind of remote sensing Objects recognition method of overhead transmission line covering area | |
CN113221760A (en) | Expressway motorcycle detection method | |
CN113139477A (en) | Method, device and equipment for training well lid detection model and computer storage medium | |
CN116310979B (en) | Image identification method, risk management and control platform and method, and safety management and control platform | |
CN105098651A (en) | Power transmission line insulator positioning method and system | |
CN114592411B (en) | Carrier parasitic type intelligent inspection method for highway damage | |
CN113033355B (en) | Abnormal target identification method and device based on intensive power transmission channel | |
Zhou et al. | Intelligent identification method for natural disasters along transmission lines based on inter-frame difference and regional convolution neural network | |
CN112633114A (en) | Unmanned aerial vehicle inspection intelligent early warning method and device for building change event | |
CN112597874A (en) | Signal lamp identification method and device and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: Yinhe building, 2008 Xinluo street, high tech Industrial Development Zone, Jinan City, Shandong Province, 250098 Patentee after: Shandong luruan Digital Technology Co.,Ltd. Address before: No.185, Jingsi Road, Shizhong District, Jinan City, Shandong Province Patentee before: SHANDONG LUNENG SOFTWARE TECHNOLOGY Co.,Ltd. |